Improve intersect_by_rank performance
#7744Comparing
rk/intersect-by-rank
(8551137
) withdevelop
(cb9b138
)-37%
- Improvement
- 9
- Regression
- 8
- Untouched
- 1181
Unknown Walltime execution environment detected
Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data. For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.Benchmarks
1198 total
for[10M_u16]
vortex-cuda/benches/for_cuda.rs::benches::benchmark_for::for_cuda-37%
94.8 µs150.6 µs
dict[10M_u32_values_u16_codes]
vortex-cuda/benches/dict_cuda.rs::benches::benchmark_dict::dict_cuda-19%
146.5 µs181.6 µs
decompress_rd[f64, (100000, 0.1)]
encodings/alp/benches/alp_compress.rs-17%
842.5 µs1,020.7 µs
decompress_rd[f64, (100000, 0.01)]
encodings/alp/benches/alp_compress.rs-17%
842.6 µs1,020.5 µs
runend[10M_i32_runlen_10]
vortex-cuda/benches/runend_cuda.rs::benches::benchmark_runend::runend_cuda-17%
159.4 µs192.5 µs
decompress_rd[f32, (100000, 0.1)]
encodings/alp/benches/alp_compress.rs-15%
495.1 µs582.5 µs
decompress_rd[f32, (100000, 0.01)]
encodings/alp/benches/alp_compress.rs-15%
495.1 µs582.5 µs
bitwise_not_vortex_buffer_mut[128]
vortex-buffer/benches/vortex_bitbuffer.rs-11%
246.1 ns275.3 ns
dynamic_dispatch_u32[10M]
vortex-cuda/benches/dynamic_dispatch_cuda.rs::benches::benchmark_dynamic_dispatch::runend_100runs+48%
142.3 µs96.3 µs
decompress_rd[f32, (100000, 0.0)]
encodings/alp/benches/alp_compress.rs+18%
583.5 µs495.6 µs
decompress_rd[f64, (10000, 0.01)]
encodings/alp/benches/alp_compress.rs+14%
138.6 µs121.9 µs
decompress_rd[f64, (10000, 0.1)]
encodings/alp/benches/alp_compress.rs+14%
138.7 µs122.1 µs
decompress_rd[f64, (10000, 0.0)]
encodings/alp/benches/alp_compress.rs+13%
138.5 µs122.1 µs
mix[100%_in/0%_out]
vortex-cuda/benches/throughput_cuda.rs::benches::benchmark_transfer_throughput::transfer_throughput_cuda+11%
500.7 µs451.6 µs
decompress_rd[f32, (10000, 0.0)]
encodings/alp/benches/alp_compress.rs+10%
94.6 µs85.7 µs
decompress_rd[f32, (10000, 0.1)]
encodings/alp/benches/alp_compress.rs+10%
90.2 µs81.8 µs
decompress_rd[f32, (10000, 0.01)]
encodings/alp/benches/alp_compress.rs+10%
90.1 µs81.9 µs
compress_rd[f64, (100000, 0.0)]
encodings/alp/benches/alp_compress.rs+5%
2.9 ms2.8 ms
compress_rd[f64, (100000, 0.01)]
encodings/alp/benches/alp_compress.rs+5%
2.9 ms2.8 ms
true_count_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+4%
678.1 ns648.9 ns
compress_rd[f64, (100000, 0.1)]
encodings/alp/benches/alp_compress.rs+4%
2.9 ms2.8 ms
decompress_rd[f64, (100000, 0.0)]
encodings/alp/benches/alp_compress.rs+4%
1,021.4 µs978.8 µs
take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+4%
25.5 µs24.5 µs
iter_vortex_buffer[128]
vortex-buffer/benches/vortex_bitbuffer.rs+3%
951.9 ns922.8 ns
patched_take_10_contiguous
encodings/fastlanes/benches/bitpacking_take.rs+3%
31 µs30.1 µs
Commits
Click on a commit to change the comparison rangeBase
develop
cb9b138
-37.03%
Improve intersect_by_rank performance
8551137
3 hours ago
by robert3005